Grounded Complex Task Segmentation for Conversational Assistants

TL;DR

This paper introduces a method to convert complex, web-based instructions into conversationally suitable steps for assistants, improving user comprehension and task execution in the recipes domain.

Contribution

It presents a novel annotation scheme and Transformer-based models for structuring instructions into manageable conversational steps, validated through user studies.

Findings

Token-based models outperform other architectures.

86% of tasks improved in conversational suitability.

Users prefer steps of manageable length and complexity.

Abstract

Following complex instructions in conversational assistants can be quite daunting due to the shorter attention and memory spans when compared to reading the same instructions. Hence, when conversational assistants walk users through the steps of complex tasks, there is a need to structure the task into manageable pieces of information of the right length and complexity. In this paper, we tackle the recipes domain and convert reading structured instructions into conversational structured ones. We annotated the structure of instructions according to a conversational scenario, which provided insights into what is expected in this setting. To computationally model the conversational step's characteristics, we tested various Transformer-based architectures, showing that a token-based approach delivers the best results. A further user study showed that users tend to favor steps of manageable complexity and length, and that the proposed methodology can improve the original web-based instructional text. Specifically, 86% of the evaluated tasks were improved from a conversational suitability point of view.